I'm dealing with a CGARCH-M model that the long and short-run volatility components have different effects on returns. Here are its mean and variance equations:

Mean equation:

$$ y_t = \alpha + \beta x_t + \gamma_1 \sqrt{\sigma_{t}^2-q_{t}}+\gamma_2 \sqrt{q_{t}} +\varepsilon_{t} $$

Variance equation:

$$ \sigma_{t}^2 = q_{t}+ \alpha_1 (\varepsilon_{t-1}^2-q_{t-1})+\varphi (\varepsilon_{t-1}^2-q_{t-1}) D_{t-1} + \beta_1 (\sigma_{t-1}^2-q_{t-1}) $$

$$ q_t = V + \rho (q_{t-1}-V) + \theta (\varepsilon_{t-1}^2-\sigma_{t+1}^2) $$

How should I estimate such models?

  • $\begingroup$ It is possible to use LaTeX on this site. Please rewrite your formulas. Also if you are asking only whether is it possible to estimate this model with Eview, this question is off-topic. $\endgroup$ – mpiktas May 25 '15 at 12:54
  • $\begingroup$ I tried to recover what the model equations are. I have not encountered the model before, so better check if the formulas are indeed OK before proceeding. $\endgroup$ – Richard Hardy May 26 '15 at 20:39

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.